{
  "schemaVersion": "1.0",
  "item": {
    "slug": "peekaboox",
    "name": "Peekaboox",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/gedigi/peekaboox",
    "canonicalUrl": "https://clawhub.ai/gedigi/peekaboox",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/peekaboox",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=peekaboox",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "LEARN_AND_TEST.md",
      "README.md",
      "SKILL.md",
      "capture.sh",
      "click.sh",
      "hotkey.sh"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/peekaboox"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/peekaboox",
    "agentPageUrl": "https://openagent3.xyz/skills/peekaboox/agent",
    "manifestUrl": "https://openagent3.xyz/skills/peekaboox/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/peekaboox/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Linux Desktop GUI Automation",
        "body": "Automate any X11 Linux desktop: capture screens, find and click elements, type, use hotkeys,\nmanage windows.\n\nPreferred screenshot interpretation path: capture with capture.sh and interpret the image directly in your OpenClaw chat (existing image-capable model connection)."
      },
      {
        "title": "Prerequisites",
        "body": "X11 session running (XFCE, GNOME on X11, KDE on X11, i3, openbox, etc.)\nDISPLAY environment variable set (usually :0)\nRun bash install.sh once to install dependencies\nNo extra key needed for screenshot interpretation when using OpenClaw's image-capable chat path"
      },
      {
        "title": "Quick Reference",
        "body": "TaskCommandTake screenshotbash capture.shScreenshot of windowbash capture.sh --window \"Firefox\"List windowsbash inspect.shActive window infobash inspect.sh --activeFind window by namebash inspect.sh --window \"Firefox\"Click at coordinatesbash click.sh --x 500 --y 300Right-clickbash click.sh --x 500 --y 300 --button rightDouble-clickbash click.sh --x 500 --y 300 --doubleClick relative to windowbash click.sh --window \"Firefox\" --x 200 --y 150Type textbash type.sh \"hello world\"Type into windowbash type.sh --window \"Terminal\" \"ls -la\"Send hotkeybash hotkey.sh \"ctrl+c\"Send Enterbash hotkey.sh \"Return\"Scroll downbash scroll.sh --direction down --amount 3Scroll up at positionbash scroll.sh --x 500 --y 300 --direction up --amount 3Focus windowbash window.sh --action focus --window \"Firefox\"Minimize windowbash window.sh --action minimize --window \"Firefox\"Maximize windowbash window.sh --action maximize --window \"Firefox\"Close windowbash window.sh --action close --window \"Firefox\"Move windowbash window.sh --action move --window \"Firefox\" --x 100 --y 50Resize windowbash window.sh --action resize --window \"Firefox\" --width 1280 --height 800"
      },
      {
        "title": "Typical Automation Workflow",
        "body": "For most GUI automation tasks, follow this pattern:\n\nCapture a screenshot with capture.sh — note the file path printed\nLook at the screenshot yourself to understand what's on screen\nFind the target element by examining the screenshot and estimating its pixel coordinates\nAct using the coordinates: click.sh --x X --y Y\nVerify by capturing another screenshot and checking the result"
      },
      {
        "title": "Example: Click the Save button in a dialog",
        "body": "# Step 1: Capture the screen\nSCREENSHOT=$(bash capture.sh | tail -1)\n\n# Step 2: Look at the screenshot (read the image file with your vision)\n# Examine the image and identify the Save button's position\n\n# Step 3: Click at the coordinates you identified\nbash click.sh --x 450 --y 320"
      },
      {
        "title": "Example: Type into a specific application",
        "body": "# Focus the terminal window and type a command\nbash type.sh --window \"Terminal\" \"ls -la\"\nbash hotkey.sh \"Return\""
      },
      {
        "title": "Example: Window management",
        "body": "# Maximize Firefox, then focus a terminal\nbash window.sh --action maximize --window \"Firefox\"\nbash window.sh --action focus --window \"Terminal\""
      },
      {
        "title": "JSON Output",
        "body": "All tools support a --json flag for machine-readable output:\n\n{\"success\": true, \"output\": \"...\", \"error\": null}\n\nOn failure:\n\n{\"success\": false, \"output\": null, \"error\": \"Error description\"}"
      },
      {
        "title": "Environment Setup",
        "body": "If DISPLAY is not set (e.g., running over SSH), set it before calling any tool:\n\nexport DISPLAY=:0\n\nFor headless servers with a virtual display:\n\nXvfb :0 -screen 0 1920x1080x24 &\nexport DISPLAY=:0"
      },
      {
        "title": "Hotkey Reference",
        "body": "Key names follow X11 conventions:\n\nKeyNameEnterReturnTabTabEscapeEscapeBackspaceBackSpaceDeleteDeleteHomeHomeEndEndPage UpPage_UpPage DownPage_DownF1-F12F1 through F12Super/WinsuperCtrlctrlAltaltShiftshift\n\nCombine with +: ctrl+c, ctrl+shift+t, alt+F4, super+d"
      },
      {
        "title": "Limitations",
        "body": "X11 only — does not work on Wayland sessions\nCannot interact with Wayland-native apps in a Wayland session\nSome apps with custom rendering (games, Electron apps with security flags) may resist automation\nScreenshot quality depends on compositor; disable compositing if captures look wrong"
      }
    ],
    "body": "Linux Desktop GUI Automation\n\nAutomate any X11 Linux desktop: capture screens, find and click elements, type, use hotkeys, manage windows.\n\nPreferred screenshot interpretation path: capture with capture.sh and interpret the image directly in your OpenClaw chat (existing image-capable model connection).\n\nPrerequisites\nX11 session running (XFCE, GNOME on X11, KDE on X11, i3, openbox, etc.)\nDISPLAY environment variable set (usually :0)\nRun bash install.sh once to install dependencies\nNo extra key needed for screenshot interpretation when using OpenClaw's image-capable chat path\nQuick Reference\nTask\tCommand\nTake screenshot\tbash capture.sh\nScreenshot of window\tbash capture.sh --window \"Firefox\"\nList windows\tbash inspect.sh\nActive window info\tbash inspect.sh --active\nFind window by name\tbash inspect.sh --window \"Firefox\"\nClick at coordinates\tbash click.sh --x 500 --y 300\nRight-click\tbash click.sh --x 500 --y 300 --button right\nDouble-click\tbash click.sh --x 500 --y 300 --double\nClick relative to window\tbash click.sh --window \"Firefox\" --x 200 --y 150\nType text\tbash type.sh \"hello world\"\nType into window\tbash type.sh --window \"Terminal\" \"ls -la\"\nSend hotkey\tbash hotkey.sh \"ctrl+c\"\nSend Enter\tbash hotkey.sh \"Return\"\nScroll down\tbash scroll.sh --direction down --amount 3\nScroll up at position\tbash scroll.sh --x 500 --y 300 --direction up --amount 3\nFocus window\tbash window.sh --action focus --window \"Firefox\"\nMinimize window\tbash window.sh --action minimize --window \"Firefox\"\nMaximize window\tbash window.sh --action maximize --window \"Firefox\"\nClose window\tbash window.sh --action close --window \"Firefox\"\nMove window\tbash window.sh --action move --window \"Firefox\" --x 100 --y 50\nResize window\tbash window.sh --action resize --window \"Firefox\" --width 1280 --height 800\nTypical Automation Workflow\n\nFor most GUI automation tasks, follow this pattern:\n\nCapture a screenshot with capture.sh — note the file path printed\nLook at the screenshot yourself to understand what's on screen\nFind the target element by examining the screenshot and estimating its pixel coordinates\nAct using the coordinates: click.sh --x X --y Y\nVerify by capturing another screenshot and checking the result\nExample: Click the Save button in a dialog\n# Step 1: Capture the screen\nSCREENSHOT=$(bash capture.sh | tail -1)\n\n# Step 2: Look at the screenshot (read the image file with your vision)\n# Examine the image and identify the Save button's position\n\n# Step 3: Click at the coordinates you identified\nbash click.sh --x 450 --y 320\n\nExample: Type into a specific application\n# Focus the terminal window and type a command\nbash type.sh --window \"Terminal\" \"ls -la\"\nbash hotkey.sh \"Return\"\n\nExample: Window management\n# Maximize Firefox, then focus a terminal\nbash window.sh --action maximize --window \"Firefox\"\nbash window.sh --action focus --window \"Terminal\"\n\nJSON Output\n\nAll tools support a --json flag for machine-readable output:\n\n{\"success\": true, \"output\": \"...\", \"error\": null}\n\n\nOn failure:\n\n{\"success\": false, \"output\": null, \"error\": \"Error description\"}\n\nEnvironment Setup\n\nIf DISPLAY is not set (e.g., running over SSH), set it before calling any tool:\n\nexport DISPLAY=:0\n\n\nFor headless servers with a virtual display:\n\nXvfb :0 -screen 0 1920x1080x24 &\nexport DISPLAY=:0\n\nHotkey Reference\n\nKey names follow X11 conventions:\n\nKey\tName\nEnter\tReturn\nTab\tTab\nEscape\tEscape\nBackspace\tBackSpace\nDelete\tDelete\nHome\tHome\nEnd\tEnd\nPage Up\tPage_Up\nPage Down\tPage_Down\nF1-F12\tF1 through F12\nSuper/Win\tsuper\nCtrl\tctrl\nAlt\talt\nShift\tshift\n\nCombine with +: ctrl+c, ctrl+shift+t, alt+F4, super+d\n\nLimitations\nX11 only — does not work on Wayland sessions\nCannot interact with Wayland-native apps in a Wayland session\nSome apps with custom rendering (games, Electron apps with security flags) may resist automation\nScreenshot quality depends on compositor; disable compositing if captures look wrong"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/gedigi/peekaboox",
    "publisherUrl": "https://clawhub.ai/gedigi/peekaboox",
    "owner": "gedigi",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/peekaboox",
    "downloadUrl": "https://openagent3.xyz/downloads/peekaboox",
    "agentUrl": "https://openagent3.xyz/skills/peekaboox/agent",
    "manifestUrl": "https://openagent3.xyz/skills/peekaboox/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/peekaboox/agent.md"
  }
}